Upload 159 files

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+excemple/40_matthew-001-01.wav filter=lfs diff=lfs merge=lfs -text
+examples/40_matthew-001-01.wav filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+__pycache__
+checkpoints

README.md

@@ -0,0 +1,12 @@
+---
+title: Demo
+emoji: 👁
+colorFrom: gray
+colorTo: gray
+sdk: gradio
+sdk_version: 5.0.1
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,52 @@
+import argparse
+import subprocess
+import torch
+import spaces
+from transformers import AutoTokenizer,AutoModelForCausalLM
+
+@torch.no_grad()
+def main():
+    # 设置命令行参数解析器
+    parser = argparse.ArgumentParser(description="启动 WebUI")
+    parser.add_argument(
+        "--llama-checkpoint-path",
+        type=str,
+        default="checkpoints/fish-speech-1.4-sft-yth-lora",
+        help="Llama 检查点路径",
+    )
+    parser.add_argument(
+        "--decoder-checkpoint-path",
+        type=str,
+        default="checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth",
+        help="解码器检查点路径",
+    )
+    parser.add_argument(
+        "--decoder-config-name",
+        type=str,
+        default="firefly_gan_vq",
+        help="解码器配置名称",
+    )
+    parser.add_argument(
+        "--device",
+        type=str,
+        default="cpu",
+        help="设备类型",
+    )
+
+    # 解析命令行参数
+    args = parser.parse_args()
+
+    # 启动 WebUI
+    subprocess.run([
+        "python",
+        "tools/webui.py",
+        "--llama-checkpoint-path", args.llama_checkpoint_path,
+        "--decoder-checkpoint-path", args.decoder_checkpoint_path,
+        "--decoder-config-name", args.decoder_config_name,
+        "--device", args.device,
+    ])
+
+if __name__ == "__main__":
+    
+    main()
+    

checkpoints/fish-speech-1.4-sft-yth-lora/config.json

@@ -0,0 +1,21 @@
+{
+    "attention_qkv_bias": false,
+    "codebook_size": 1024,
+    "dim": 1024,
+    "dropout": 0.1,
+    "head_dim": 64,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "max_seq_len": 4096,
+    "model_type": "dual_ar",
+    "n_fast_layer": 4,
+    "n_head": 16,
+    "n_layer": 24,
+    "n_local_heads": 2,
+    "norm_eps": 1e-06,
+    "num_codebooks": 8,
+    "rope_base": 1000000.0,
+    "tie_word_embeddings": false,
+    "use_gradient_checkpointing": true,
+    "vocab_size": 32000
+}

checkpoints/fish-speech-1.4-sft-yth-lora/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a27344ad35a0514f9cd60869276d2b5bf23dde6b39fe8a0421050e06984246
+size 988997246

checkpoints/fish-speech-1.4-sft-yth-lora/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_sequence|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_sequence|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/fish-speech-1.4-sft-yth-lora/tokenizer_config.json

@@ -0,0 +1,82 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|begin_of_sequence|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|end_of_sequence|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|semantic|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|mel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|reserve_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|reserve_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_sequence|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_sequence|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoints/fish-speech-1.4/README.md

@@ -0,0 +1,61 @@
+---
+tags:
+- text-to-speech
+license: cc-by-nc-sa-4.0
+language:
+- zh
+- en
+- de
+- ja
+- fr
+- es
+- ko
+- ar
+pipeline_tag: text-to-speech
+inference: false
+extra_gated_prompt: >-
+  You agree to not use the model to generate contents that violate DMCA or local
+  laws.
+extra_gated_fields:
+  Country: country
+  Specific date: date_picker
+  I agree to use this model for non-commercial use ONLY: checkbox
+---
+
+
+# Fish Speech V1.4
+
+**Fish Speech V1.4** is a leading text-to-speech (TTS) model trained on 700k hours of audio data in multiple languages.
+
+Supported languages:
+- English (en) ~300k hours 
+- Chinese (zh) ~300k hours
+- German (de) ~20k hours
+- Japanese (ja) ~20k hours
+- French (fr) ~20k hours
+- Spanish (es) ~20k hours
+- Korean (ko) ~20k hours
+- Arabic (ar) ~20k hours
+
+Please refer to [Fish Speech Github](https://github.com/fishaudio/fish-speech) for more info.  
+Demo available at [Fish Audio](https://fish.audio/).
+
+## Citation
+
+If you found this repository useful, please consider citing this work:
+
+```
+@misc{fish-speech-v1.4,
+  author = {Shijia Liao, Tianyu Li, etc},
+  title = {Fish Speech V1.4},
+  year = {2024},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/fishaudio/fish-speech}}
+}
+```
+
+## License
+
+This model is permissively licensed under the BY-CC-NC-SA-4.0 license.
+The source code is released under BSD-3-Clause license.

checkpoints/fish-speech-1.4/config.json

@@ -0,0 +1,21 @@
+{
+    "attention_qkv_bias": false,
+    "codebook_size": 1024,
+    "dim": 1024,
+    "dropout": 0.1,
+    "head_dim": 64,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "max_seq_len": 4096,
+    "model_type": "dual_ar",
+    "n_fast_layer": 4,
+    "n_head": 16,
+    "n_layer": 24,
+    "n_local_heads": 2,
+    "norm_eps": 1e-06,
+    "num_codebooks": 8,
+    "rope_base": 1000000.0,
+    "tie_word_embeddings": false,
+    "use_gradient_checkpointing": true,
+    "vocab_size": 32000
+}

checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b81dbf753224a156c3fe139b88bf0b9a0f54b11bee864f95e66511c3ccd754
+size 188518579

checkpoints/fish-speech-1.4/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1cfa4b59c37f58d22e0626a53cec61db79390d7d0733b6402bf6f69fe58b93
+size 988988542

checkpoints/fish-speech-1.4/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_sequence|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_sequence|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/fish-speech-1.4/tokenizer_config.json

@@ -0,0 +1,82 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|begin_of_sequence|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|end_of_sequence|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|semantic|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|mel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|reserve_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|reserve_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_sequence|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_sequence|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

configs/base.yaml

@@ -0,0 +1,87 @@
+# Base configuration for training a model
+paths:
+  run_dir: results/${project}
+  ckpt_dir: ${paths.run_dir}/checkpoints
+
+hydra:
+  run:
+    dir: ${paths.run_dir}
+
+# Lightning Trainer
+trainer:
+  _target_: lightning.pytorch.trainer.Trainer
+
+  default_root_dir: ${paths.run_dir}
+  accelerator: gpu
+  num_nodes: 1
+  devices: auto
+  strategy:
+    _target_: lightning.pytorch.strategies.DDPStrategy
+    process_group_backend: nccl  # This should be override when training on windows
+
+  precision: bf16-mixed
+
+  # disable validation by epoch end
+  check_val_every_n_epoch: null
+  val_check_interval: 5000
+  max_steps: 100_000
+
+  # Use torch.backends.cudnn.benchmark to speed up training
+  benchmark: true
+
+# Callbacks
+callbacks:
+  model_checkpoint:
+    _target_: lightning.pytorch.callbacks.ModelCheckpoint
+    dirpath: ${paths.ckpt_dir}
+    filename: "step_{step:09d}"
+    save_last: false # additionally always save an exact copy of the last checkpoint to a file last.ckpt
+    save_top_k: 5 # save 5 latest checkpoints
+    monitor: step # use step to monitor checkpoints
+    mode: max # save the latest checkpoint with the highest global_step
+    every_n_epochs: null # don't save checkpoints by epoch end
+    every_n_train_steps: 5000 # save checkpoints every 5000 steps
+    auto_insert_metric_name: false
+
+  model_summary:
+    _target_: lightning.pytorch.callbacks.ModelSummary
+    max_depth: 2 # the maximum depth of layer nesting that the summary will include
+
+  learning_rate_monitor:
+    _target_: lightning.pytorch.callbacks.LearningRateMonitor
+    logging_interval: step
+    log_momentum: false
+
+  grad_norm_monitor:
+    _target_: fish_speech.callbacks.GradNormMonitor
+    norm_type: 2
+    logging_interval: step
+
+# Logger
+logger:
+  tensorboard:
+    _target_: lightning.pytorch.loggers.tensorboard.TensorBoardLogger
+    save_dir: "${paths.run_dir}/tensorboard/"
+    name: null
+    log_graph: false
+    default_hp_metric: true
+    prefix: ""
+
+  # wandb:
+  #   _target_: lightning.pytorch.loggers.wandb.WandbLogger
+  #   # name: "" # name of the run (normally generated by wandb)
+  #   save_dir: "${paths.run_dir}"
+  #   offline: False
+  #   id: null # pass correct id to resume experiment!
+  #   anonymous: null # enable anonymous logging
+  #   project: "fish-speech"
+  #   log_model: False # upload lightning ckpts
+  #   prefix: "" # a string to put at the beginning of metric keys
+  #   # entity: "" # set to name of your wandb team
+  #   group: ""
+  #   tags: ["vq", "hq", "finetune"]
+  #   job_type: ""
+    
+# Loop
+train: true
+test: false

configs/firefly_gan_vq.yaml

@@ -0,0 +1,33 @@
+_target_: fish_speech.models.vqgan.modules.firefly.FireflyArchitecture
+spec_transform:
+  _target_: fish_speech.utils.spectrogram.LogMelSpectrogram
+  sample_rate: 44100
+  n_mels: 160
+  n_fft: 2048
+  hop_length: 512
+  win_length: 2048
+backbone:
+  _target_: fish_speech.models.vqgan.modules.firefly.ConvNeXtEncoder
+  input_channels: 160
+  depths: [3, 3, 9, 3]
+  dims: [128, 256, 384, 512]
+  drop_path_rate: 0.2
+  kernel_size: 7
+head:
+  _target_: fish_speech.models.vqgan.modules.firefly.HiFiGANGenerator
+  hop_length: 512
+  upsample_rates: [8, 8, 2, 2, 2]  # aka. strides
+  upsample_kernel_sizes: [16, 16, 4, 4, 4]
+  resblock_kernel_sizes: [3, 7, 11]
+  resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+  num_mels: 512
+  upsample_initial_channel: 512
+  pre_conv_kernel_size: 13
+  post_conv_kernel_size: 13
+quantizer:
+  _target_: fish_speech.models.vqgan.modules.fsq.DownsampleFiniteScalarQuantize
+  input_dim: 512
+  n_groups: 8
+  n_codebooks: 1
+  levels: [8, 5, 5, 5]
+  downsample_factor: [2, 2]

configs/lora/r_8_alpha_16.yaml

@@ -0,0 +1,4 @@
+_target_: fish_speech.models.text2semantic.lora.LoraConfig
+r: 8
+lora_alpha: 16
+lora_dropout: 0.01

configs/text2semantic_finetune.yaml

@@ -0,0 +1,83 @@
+defaults:
+  - base
+  - _self_
+
+project: text2semantic_finetune_dual_ar
+max_length: 4096
+pretrained_ckpt_path: checkpoints/fish-speech-1.4
+
+# Lightning Trainer
+trainer:
+  accumulate_grad_batches: 1
+  gradient_clip_val: 1.0
+  gradient_clip_algorithm: "norm"
+  max_steps: 1000
+  precision: bf16-true
+  limit_val_batches: 10
+  val_check_interval: 100
+
+# Dataset Configuration
+tokenizer:
+  _target_: transformers.AutoTokenizer.from_pretrained
+  pretrained_model_name_or_path: ${pretrained_ckpt_path}
+
+# Dataset Configuration
+train_dataset:
+  _target_: fish_speech.datasets.semantic.AutoTextSemanticInstructionDataset
+  proto_files:
+    - data/protos
+  tokenizer: ${tokenizer}
+  causal: true
+  max_length: ${max_length}
+  use_speaker: false
+  interactive_prob: 0.7
+
+val_dataset:
+  _target_: fish_speech.datasets.semantic.AutoTextSemanticInstructionDataset
+  proto_files:
+    - data/protos
+  tokenizer: ${tokenizer}
+  causal: true
+  max_length: ${max_length}
+  use_speaker: false
+  interactive_prob: 0.7
+
+data:
+  _target_: fish_speech.datasets.semantic.SemanticDataModule
+  train_dataset: ${train_dataset}
+  val_dataset: ${val_dataset}
+  num_workers: 4
+  batch_size: 8
+  tokenizer: ${tokenizer}
+  max_length: ${max_length}
+
+# Model Configuration
+model:
+  _target_: fish_speech.models.text2semantic.lit_module.TextToSemantic
+  model: 
+    _target_: fish_speech.models.text2semantic.llama.BaseTransformer.from_pretrained
+    path: ${pretrained_ckpt_path}
+    load_weights: true
+    max_length: ${max_length}
+    lora_config: null
+
+  optimizer:
+    _target_: torch.optim.AdamW
+    _partial_: true
+    lr: 1e-4
+    weight_decay: 0
+    betas: [0.9, 0.95]
+    eps: 1e-5
+
+  lr_scheduler:
+    _target_: torch.optim.lr_scheduler.LambdaLR
+    _partial_: true
+    lr_lambda:
+      _target_: fish_speech.scheduler.get_constant_schedule_with_warmup_lr_lambda
+      _partial_: true
+      num_warmup_steps: 10
+
+# Callbacks
+callbacks:
+  model_checkpoint:
+    every_n_train_steps: ${trainer.val_check_interval}

examples/40_matthew-001-01.lab

@@ -0,0 +1 @@
+Miyan qaniy qu binkgan bbinkesan na Yesu:Yesu Kristo ga kinbahan na Tabite, Tabite ga kinbahan na Aburaham.

examples/40_matthew-001-01.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173b0800783e09808e2a1c74f0a8f85fbccb705289986f5dd63ef60a821ea805
+size 1200330

fish_speech/callbacks/__init__.py

@@ -0,0 +1,3 @@
+from .grad_norm import GradNormMonitor
+
+__all__ = ["GradNormMonitor"]

fish_speech/callbacks/grad_norm.py

@@ -0,0 +1,113 @@
+from typing import Optional, Union
+
+import lightning.pytorch as pl
+import torch
+from lightning import LightningModule, Trainer
+from lightning.pytorch.callbacks import Callback
+from torch import Tensor, nn
+from torch.utils._foreach_utils import (
+    _group_tensors_by_device_and_dtype,
+    _has_foreach_support,
+)
+
+
+@torch.no_grad()
+def grad_norm(
+    parameters: Union[Tensor, list[Tensor]],
+    norm_type: float = 2.0,
+) -> float:
+    """
+    Returns the norm of the gradients of the given parameters.
+
+    Args:
+        parameters (Iterable[Tensor] or Tensor): an iterable of Tensors or a
+            single Tensor that will have gradients normalized
+        norm_type (float): type of the used p-norm.
+
+    Returns:
+        Total norm of the parameter gradients (viewed as a single vector).
+    """  # noqa: E501
+
+    if isinstance(parameters, Tensor):
+        parameters = [parameters]
+
+    grads = [p.grad for p in parameters if p.grad is not None]
+    if len(grads) == 0:
+        return None
+
+    first_device = grads[0].device
+    grouped_grads: dict[
+        tuple[torch.device, torch.dtype], list[list[Tensor]]
+    ] = _group_tensors_by_device_and_dtype(
+        [[g.detach() for g in grads]]
+    )  # type: ignore[assignment]
+
+    norms = []
+    for (device, _), ([grads], _) in grouped_grads.items():
+        if _has_foreach_support(grads, device=device):
+            norms.extend(torch._foreach_norm(grads, norm_type))
+        else:
+            norms.extend([torch.norm(g, norm_type) for g in grads])
+
+    return torch.norm(torch.stack([norm.to(first_device) for norm in norms]), norm_type)
+
+
+class GradNormMonitor(Callback):
+    """
+    Callback that computes the gradient norm of the model parameters.
+    """
+
+    def __init__(
+        self,
+        norm_type: float = 2.0,
+        logging_interval: str = "step",
+        sub_module: Optional[Union[str, list[str]]] = None,
+    ) -> None:
+        """
+        Args:
+            norm_type (float): type of the used p-norm.
+            logging_interval (str): "step" or "epoch".
+        """
+        super().__init__()
+
+        self.norm_type = norm_type
+        self.logging_interval = logging_interval
+        self.sub_module = sub_module
+
+    def on_after_backward(self, trainer: Trainer, model: LightningModule) -> None:
+        """
+        Computes the gradient norm of the model parameters and logs it to the logger.
+
+        Args:
+            trainer (Trainer): The trainer object
+            model (LightningModule): The current lightningModule
+        """
+
+        lightning_model = model
+
+        if self.sub_module is None:
+            return self.log_sub_module_grad_norm(lightning_model, model, "")
+
+        sub_modules = self.sub_module
+        if isinstance(sub_modules, str):
+            sub_modules = [sub_modules]
+
+        for sub_module in sub_modules:
+            self.log_sub_module_grad_norm(
+                lightning_model, getattr(model, sub_module), f"/{sub_module}"
+            )
+
+    def log_sub_module_grad_norm(
+        self, lightning_model: LightningModule, model: nn.Module, path: str
+    ) -> None:
+        grad_norm_val = grad_norm(model.parameters(), self.norm_type)
+        if grad_norm_val is None:
+            return
+
+        on_step = self.logging_interval == "step"
+        lightning_model.log(
+            f"train{path}/grad_norm",
+            grad_norm_val,
+            on_step=on_step,
+            on_epoch=not on_step,
+        )

fish_speech/configs/base.yaml

@@ -0,0 +1,87 @@
+# Base configuration for training a model
+paths:
+  run_dir: results/${project}
+  ckpt_dir: ${paths.run_dir}/checkpoints
+
+hydra:
+  run:
+    dir: ${paths.run_dir}
+
+# Lightning Trainer
+trainer:
+  _target_: lightning.pytorch.trainer.Trainer
+
+  default_root_dir: ${paths.run_dir}
+  accelerator: gpu
+  num_nodes: 1
+  devices: auto
+  strategy:
+    _target_: lightning.pytorch.strategies.DDPStrategy
+    process_group_backend: nccl  # This should be override when training on windows
+
+  precision: bf16-mixed
+
+  # disable validation by epoch end
+  check_val_every_n_epoch: null
+  val_check_interval: 5000
+  max_steps: 100_000
+
+  # Use torch.backends.cudnn.benchmark to speed up training
+  benchmark: true
+
+# Callbacks
+callbacks:
+  model_checkpoint:
+    _target_: lightning.pytorch.callbacks.ModelCheckpoint
+    dirpath: ${paths.ckpt_dir}
+    filename: "step_{step:09d}"
+    save_last: false # additionally always save an exact copy of the last checkpoint to a file last.ckpt
+    save_top_k: 5 # save 5 latest checkpoints
+    monitor: step # use step to monitor checkpoints
+    mode: max # save the latest checkpoint with the highest global_step
+    every_n_epochs: null # don't save checkpoints by epoch end
+    every_n_train_steps: 5000 # save checkpoints every 5000 steps
+    auto_insert_metric_name: false
+
+  model_summary:
+    _target_: lightning.pytorch.callbacks.ModelSummary
+    max_depth: 2 # the maximum depth of layer nesting that the summary will include
+
+  learning_rate_monitor:
+    _target_: lightning.pytorch.callbacks.LearningRateMonitor
+    logging_interval: step
+    log_momentum: false
+
+  grad_norm_monitor:
+    _target_: fish_speech.callbacks.GradNormMonitor
+    norm_type: 2
+    logging_interval: step
+
+# Logger
+logger:
+  tensorboard:
+    _target_: lightning.pytorch.loggers.tensorboard.TensorBoardLogger
+    save_dir: "${paths.run_dir}/tensorboard/"
+    name: null
+    log_graph: false
+    default_hp_metric: true
+    prefix: ""
+
+  # wandb:
+  #   _target_: lightning.pytorch.loggers.wandb.WandbLogger
+  #   # name: "" # name of the run (normally generated by wandb)
+  #   save_dir: "${paths.run_dir}"
+  #   offline: False
+  #   id: null # pass correct id to resume experiment!
+  #   anonymous: null # enable anonymous logging
+  #   project: "fish-speech"
+  #   log_model: False # upload lightning ckpts
+  #   prefix: "" # a string to put at the beginning of metric keys
+  #   # entity: "" # set to name of your wandb team
+  #   group: ""
+  #   tags: ["vq", "hq", "finetune"]
+  #   job_type: ""
+    
+# Loop
+train: true
+test: false

fish_speech/configs/firefly_gan_vq.yaml

@@ -0,0 +1,33 @@
+_target_: fish_speech.models.vqgan.modules.firefly.FireflyArchitecture
+spec_transform:
+  _target_: fish_speech.utils.spectrogram.LogMelSpectrogram
+  sample_rate: 44100
+  n_mels: 160
+  n_fft: 2048
+  hop_length: 512
+  win_length: 2048
+backbone:
+  _target_: fish_speech.models.vqgan.modules.firefly.ConvNeXtEncoder
+  input_channels: 160
+  depths: [3, 3, 9, 3]
+  dims: [128, 256, 384, 512]
+  drop_path_rate: 0.2
+  kernel_size: 7
+head:
+  _target_: fish_speech.models.vqgan.modules.firefly.HiFiGANGenerator
+  hop_length: 512
+  upsample_rates: [8, 8, 2, 2, 2]  # aka. strides
+  upsample_kernel_sizes: [16, 16, 4, 4, 4]
+  resblock_kernel_sizes: [3, 7, 11]
+  resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+  num_mels: 512
+  upsample_initial_channel: 512
+  pre_conv_kernel_size: 13
+  post_conv_kernel_size: 13
+quantizer:
+  _target_: fish_speech.models.vqgan.modules.fsq.DownsampleFiniteScalarQuantize
+  input_dim: 512
+  n_groups: 8
+  n_codebooks: 1
+  levels: [8, 5, 5, 5]
+  downsample_factor: [2, 2]

fish_speech/configs/lora/r_8_alpha_16.yaml

@@ -0,0 +1,4 @@
+_target_: fish_speech.models.text2semantic.lora.LoraConfig
+r: 8
+lora_alpha: 16
+lora_dropout: 0.01

fish_speech/configs/text2semantic_finetune.yaml

@@ -0,0 +1,83 @@
+defaults:
+  - base
+  - _self_
+
+project: text2semantic_finetune_dual_ar
+max_length: 4096
+pretrained_ckpt_path: checkpoints/fish-speech-1.4
+
+# Lightning Trainer
+trainer:
+  accumulate_grad_batches: 1
+  gradient_clip_val: 1.0
+  gradient_clip_algorithm: "norm"
+  max_steps: 1000
+  precision: bf16-true
+  limit_val_batches: 10
+  val_check_interval: 100
+
+# Dataset Configuration
+tokenizer:
+  _target_: transformers.AutoTokenizer.from_pretrained
+  pretrained_model_name_or_path: ${pretrained_ckpt_path}
+
+# Dataset Configuration
+train_dataset:
+  _target_: fish_speech.datasets.semantic.AutoTextSemanticInstructionDataset
+  proto_files:
+    - data/protos
+  tokenizer: ${tokenizer}
+  causal: true
+  max_length: ${max_length}
+  use_speaker: false
+  interactive_prob: 0.7
+
+val_dataset:
+  _target_: fish_speech.datasets.semantic.AutoTextSemanticInstructionDataset
+  proto_files:
+    - data/protos
+  tokenizer: ${tokenizer}
+  causal: true
+  max_length: ${max_length}
+  use_speaker: false
+  interactive_prob: 0.7
+
+data:
+  _target_: fish_speech.datasets.semantic.SemanticDataModule
+  train_dataset: ${train_dataset}
+  val_dataset: ${val_dataset}
+  num_workers: 4
+  batch_size: 8
+  tokenizer: ${tokenizer}
+  max_length: ${max_length}
+
+# Model Configuration
+model:
+  _target_: fish_speech.models.text2semantic.lit_module.TextToSemantic
+  model: 
+    _target_: fish_speech.models.text2semantic.llama.BaseTransformer.from_pretrained
+    path: ${pretrained_ckpt_path}
+    load_weights: true
+    max_length: ${max_length}
+    lora_config: null
+
+  optimizer:
+    _target_: torch.optim.AdamW
+    _partial_: true
+    lr: 1e-4
+    weight_decay: 0
+    betas: [0.9, 0.95]
+    eps: 1e-5
+
+  lr_scheduler:
+    _target_: torch.optim.lr_scheduler.LambdaLR
+    _partial_: true
+    lr_lambda:
+      _target_: fish_speech.scheduler.get_constant_schedule_with_warmup_lr_lambda
+      _partial_: true
+      num_warmup_steps: 10
+
+# Callbacks
+callbacks:
+  model_checkpoint:
+    every_n_train_steps: ${trainer.val_check_interval}

fish_speech/conversation.py

@@ -0,0 +1,2 @@
+SEMANTIC_TOKEN = "<|semantic|>"
+CODEBOOK_PAD_TOKEN_ID = 0

fish_speech/datasets/concat_repeat.py

@@ -0,0 +1,53 @@
+import bisect
+import random
+from typing import Iterable
+
+from torch.utils.data import Dataset, IterableDataset
+
+
+class ConcatRepeatDataset(Dataset):
+    datasets: list[Dataset]
+    cumulative_sizes: list[int]
+    repeats: list[int]
+
+    @staticmethod
+    def cumsum(sequence, repeats):
+        r, s = [], 0
+        for dataset, repeat in zip(sequence, repeats):
+            l = len(dataset) * repeat
+            r.append(l + s)
+            s += l
+        return r
+
+    def __init__(self, datasets: Iterable[Dataset], repeats: list[int]):
+        super().__init__()
+
+        self.datasets = list(datasets)
+        self.repeats = repeats
+
+        assert len(self.datasets) > 0, "datasets should not be an empty iterable"
+        assert len(self.datasets) == len(
+            repeats
+        ), "datasets and repeats should have the same length"
+
+        for d in self.datasets:
+            assert not isinstance(
+                d, IterableDataset
+            ), "ConcatRepeatDataset does not support IterableDataset"
+
+        self.cumulative_sizes = self.cumsum(self.datasets, self.repeats)
+
+    def __len__(self):
+        return self.cumulative_sizes[-1]
+
+    def __getitem__(self, idx):
+        dataset_idx = bisect.bisect_right(self.cumulative_sizes, idx)
+
+        if dataset_idx == 0:
+            sample_idx = idx
+        else:
+            sample_idx = idx - self.cumulative_sizes[dataset_idx - 1]
+
+        dataset = self.datasets[dataset_idx]
+
+        return dataset[sample_idx % len(dataset)]

fish_speech/datasets/protos/text-data.proto

@@ -0,0 +1,24 @@
+syntax = "proto3";
+
+package text_data;
+
+message Semantics {
+    repeated uint32 values = 1;
+}
+
+message Sentence {
+    repeated string texts = 1;
+    repeated Semantics semantics = 3;
+}
+
+message TextData {
+    string source = 1;
+    string name = 2;
+    repeated Sentence sentences = 4;
+}
+
+message SampledData {
+    string source = 1;
+    string name = 2;
+    repeated Sentence samples = 3;
+}

fish_speech/datasets/protos/text_data_pb2.py

@@ -0,0 +1,33 @@
+# -*- coding: utf-8 -*-
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# source: text-data.proto
+# Protobuf Python Version: 4.25.1
+"""Generated protocol buffer code."""
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import descriptor_pool as _descriptor_pool
+from google.protobuf import symbol_database as _symbol_database
+from google.protobuf.internal import builder as _builder
+
+# @@protoc_insertion_point(imports)
+
+_sym_db = _symbol_database.Default()
+
+
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(
+    b'\n\x0ftext-data.proto\x12\ttext_data"\x1b\n\tSemantics\x12\x0e\n\x06values\x18\x01 \x03(\r"B\n\x08Sentence\x12\r\n\x05texts\x18\x01 \x03(\t\x12\'\n\tsemantics\x18\x03 \x03(\x0b\x32\x14.text_data.Semantics"P\n\x08TextData\x12\x0e\n\x06source\x18\x01 \x01(\t\x12\x0c\n\x04name\x18\x02 \x01(\t\x12&\n\tsentences\x18\x04 \x03(\x0b\x32\x13.text_data.Sentence"Q\n\x0bSampledData\x12\x0e\n\x06source\x18\x01 \x01(\t\x12\x0c\n\x04name\x18\x02 \x01(\t\x12$\n\x07samples\x18\x03 \x03(\x0b\x32\x13.text_data.Sentenceb\x06proto3'
+)
+
+_globals = globals()
+_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
+_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, "text_data_pb2", _globals)
+if _descriptor._USE_C_DESCRIPTORS == False:
+    DESCRIPTOR._options = None
+    _globals["_SEMANTICS"]._serialized_start = 30
+    _globals["_SEMANTICS"]._serialized_end = 57
+    _globals["_SENTENCE"]._serialized_start = 59
+    _globals["_SENTENCE"]._serialized_end = 125
+    _globals["_TEXTDATA"]._serialized_start = 127
+    _globals["_TEXTDATA"]._serialized_end = 207
+    _globals["_SAMPLEDDATA"]._serialized_start = 209
+    _globals["_SAMPLEDDATA"]._serialized_end = 290
+# @@protoc_insertion_point(module_scope)

fish_speech/datasets/protos/text_data_stream.py

@@ -0,0 +1,36 @@
+import struct
+
+from .text_data_pb2 import TextData
+
+
+def read_pb_stream(f):
+    while True:
+        buf = f.read(4)
+        if len(buf) == 0:
+            break
+        size = struct.unpack("I", buf)[0]
+        buf = f.read(size)
+        text_data = TextData()
+        text_data.ParseFromString(buf)
+        yield text_data
+
+
+def write_pb_stream(f, text_data):
+    buf = text_data.SerializeToString()
+    f.write(struct.pack("I", len(buf)))
+    f.write(buf)
+
+
+def pack_pb_stream(text_data):
+    buf = text_data.SerializeToString()
+    return struct.pack("I", len(buf)) + buf
+
+
+def split_pb_stream(f):
+    while True:
+        head = f.read(4)
+        if len(head) == 0:
+            break
+        size = struct.unpack("I", head)[0]
+        buf = f.read(size)
+        yield head + buf

fish_speech/datasets/semantic.py

@@ -0,0 +1,496 @@
+import random
+from dataclasses import dataclass
+from itertools import chain
+from pathlib import Path
+from random import Random
+from typing import Optional, Union
+
+import numpy as np
+import pyarrow.parquet as pq
+import torch
+import torch.nn.functional as F
+from datasets.download.streaming_download_manager import xopen
+from huggingface_hub import HfApi
+from lightning import LightningDataModule
+from torch.distributed import get_rank, get_world_size, is_initialized
+from torch.utils.data import DataLoader, IterableDataset, get_worker_info
+from transformers import AutoTokenizer
+
+from fish_speech.conversation import CODEBOOK_PAD_TOKEN_ID
+from fish_speech.datasets.protos.text_data_pb2 import SampledData
+from fish_speech.datasets.protos.text_data_stream import read_pb_stream
+from fish_speech.text.clean import clean_text
+from fish_speech.utils import RankedLogger
+from fish_speech.utils.braceexpand import braceexpand
+
+log = RankedLogger(__name__, rank_zero_only=True)
+
+
+def split_by_rank_worker(files):
+    # We need to know the total number of devices
+    # to split the data properly
+
+    total_devices = 1
+    if is_initialized():
+        total_devices = get_world_size()
+
+    worker_info = get_worker_info()
+    if worker_info is not None:
+        total_devices *= worker_info.num_workers
+
+    if len(files) < total_devices:
+        # Repeat the files N times to match the number of devices
+        files = files * (total_devices // len(files) + 1)
+
+    # DDP
+    if is_initialized():
+        files = files[get_rank() :: get_world_size()]
+
+    # Split by worker
+    if worker_info is not None:
+        files = files[worker_info.id :: worker_info.num_workers]
+
+    return files
+
+
+class AutoTextSemanticInstructionDataset(IterableDataset):
+    """
+    Auto Augment Dataset by Speaker
+
+    1. Random concatenate multiple sentences from the same speaker to form a longer sentence
+    2. Automatically normalize the text
+
+    For interactive mode, we use the following format (multiple sequences):
+    <s> [INST] [SPK: speaker] text [/INST] ... [INST] text [/INST] </s>
+
+    For non-interactive mode, we use the following format (one long sequence):
+    <s> [INST] text [/INST] ... </s>
+    """
+
+    def __init__(
+        self,
+        proto_files: list[str],
+        seed: int = 42,
+        interactive_prob: float = 0.5,
+        max_length: int = 1024,
+        tokenizer: AutoTokenizer = None,
+        use_speaker: bool | float = True,
+        causal: bool = True,
+        num_codebooks: Optional[int] = None,
+        skip_text_prob: float = 0.0,
+    ):
+        """
+        Args:
+            proto_files: proto buf files if using local data
+            seed: random seed
+            interactive_prob: probability to use interactive mode
+            max_length: max length of the text
+            tokenizer: tokenizer
+            use_speaker: include speaker information in the prompt
+            causal: use causal sampling when using local data, disable will lead to random sampling
+            num_codebooks: number of codebooks, if None, it will be automatically detected
+            skip_text_prob: probability to skip the text (audio only), this only applies to interactive mode
+        """
+
+        super().__init__()
+
+        assert 0 <= interactive_prob <= 1, "interactive_prob must be in [0, 1]"
+
+        self.seed = seed
+        self.max_length = max_length
+        self.tokenizer = tokenizer
+        self.interactive_prob = interactive_prob
+        self.use_speaker = use_speaker
+        self.proto_files = proto_files
+        self.causal = causal
+        self.num_codebooks = num_codebooks
+        self.skip_text_prob = skip_text_prob
+
+        self.semantic_token_id = self.tokenizer.convert_tokens_to_ids("<|semantic|>")
+        self.groups = None
+
+    def init_mock_data_server(self):
+        if self.groups is not None:
+            return
+
+        # Expand the proto files
+        expanded_proto_files = []
+        for filename in self.proto_files:
+            for i in braceexpand(filename):
+                i = Path(i)
+                if i.is_file():
+                    expanded_proto_files.append(i)
+                elif i.is_dir():
+                    expanded_proto_files.extend(i.rglob("*.proto"))
+                    expanded_proto_files.extend(i.rglob("*.protos"))
+                else:
+                    raise ValueError(f"{i} is not a file or directory")
+
+        expanded_proto_files = sorted(expanded_proto_files)
+        Random(self.seed).shuffle(expanded_proto_files)
+
+        self.groups = []
+        shard_proto_files = split_by_rank_worker(expanded_proto_files)
+        log.info(
+            f"Reading {len(shard_proto_files)} / {len(expanded_proto_files)} files"
+        )
+
+        count = 0
+        for filename in shard_proto_files:
+            with open(filename, "rb") as f:
+                for text_data in read_pb_stream(f):
+                    self.groups.append(text_data)
+                    count += 1
+
+        log.info(f"Read total {count} groups of data")
+
+        # Shuffle the lines
+        Random(self.seed).shuffle(self.groups)
+        self.group_weights = [len(i.sentences) for i in self.groups]
+
+    def __iter__(self):
+        while True:
+            yield self.augment()
+
+    def tokenize_sentence(self, sentence: str):
+        sentence = clean_text(sentence)
+        tokens = self.tokenizer.encode(
+            f"{sentence}",
+            max_length=10**6,
+            add_special_tokens=False,
+            truncation=False,
+        )
+        return sentence, len(tokens)
+
+    def sample_data(self):
+        if self.groups is None:
+            self.init_mock_data_server()
+
+        # Shuffle unique lines, estimate that each sample is at least 20 tokens
+        num_samples = self.max_length // 20
+
+        # choice group based on their number of samples
+        group = random.choices(self.groups, weights=self.group_weights, k=1)[0]
+
+        if self.causal:
+            # Sample in order
+            if num_samples >= len(group.sentences):
+                samples = group.sentences
+            else:
+                begin = random.randint(0, len(group.sentences) - num_samples)
+                samples = group.sentences[begin : begin + num_samples]
+        else:
+            samples = random.choices(
+                group.sentences, k=min(num_samples, len(group.sentences))
+            )
+
+        return SampledData(
+            source=group.source,
+            name=group.name,
+            samples=samples,
+        )
+
+    def augment(self):
+        final_text, final_semantic = [], []
+        response = self.sample_data()
+        if len(response.samples) == 0:
+            # Invalid group
+            return None
+
+        samples = list(response.samples)
+        idx = 0
+        use_interactive = random.random() < self.interactive_prob
+
+        if use_interactive is False:
+            # Random sample based on speaker using a truncated normal distribution
+            a = torch.tensor([0], dtype=torch.float32)
+            torch.nn.init.trunc_normal_(
+                a,
+                mean=self.max_length // 2,
+                std=self.max_length // 4,
+                a=10,
+                b=self.max_length,
+            )
+            remaining_tokens = a.long().item() - 4
+        else:
+            remaining_tokens = self.max_length
+
+        # Use speaker
+        if isinstance(self.use_speaker, float):
+            use_speaker = random.random() < self.use_speaker
+        else:
+            use_speaker = self.use_speaker
+
+        all_tokens, all_labels = [], []
+        while remaining_tokens > 0 and len(samples) > 0:
+            sentence = samples.pop(0)
+
+            text = random.choice(sentence.texts)
+            text, length = self.tokenize_sentence(text)
+            remaining_tokens -= length + len(sentence.semantics[0].values)
+
+            if use_interactive is False:
+                final_text.append(text)
+                final_semantic.append(sentence.semantics)
+            else:
+                # For interactive mode, we only apply speaker for the first sentence
+                # [INST] [SPK: speaker] text [/INST] ... [INST] text [/INST]
+                tokens, labels = self.pack_sentences(
+                    sentences=[text],
+                    semantics=[sentence.semantics],
+                    speaker=response.name if use_speaker else None,
+                    skip_text=random.random() < self.skip_text_prob,
+                )
+
+                all_tokens.append(tokens)
+                all_labels.append(labels)
+
+            idx += 1
+
+        if use_interactive is False:
+            tokens, labels = self.pack_sentences(
+                final_text,
+                semantics=final_semantic,
+                speaker=response.name if use_speaker else None,
+            )
+            all_tokens.append(tokens)
+            all_labels.append(labels)
+
+        tokens = torch.cat(all_tokens, dim=1)
+        labels = torch.cat(all_labels, dim=1)
+
+        # Verify that the length is correct
+        assert tokens.size(1) == labels.size(1), f"{tokens.size(1)} != {labels.size(1)}"
+
+        data = {"tokens": tokens, "labels": labels}
+
+        return data
+
+    def pack_sentences(
+        self,
+        sentences: list[str],
+        semantics: list,
+        speaker: Optional[str] = None,
+        skip_text: bool = False,
+    ):
+        if speaker is None:
+            speaker = "assistant"
+
+        cated_sentences = " ".join(sentences)
+        if skip_text:
+            cated_sentences = "<|skip_text|>"
+
+        final_text = "<|im_start|>user\n" + cated_sentences + "<|im_end|>"
+        final_text = final_text + f"<|im_start|>{speaker}\n"
+
+        encoded = self.tokenizer.encode(
+            final_text,
+            add_special_tokens=False,
+            truncation=False,
+            max_length=10**6,
+        )
+        semantic_length = sum([len(i[0].values) for i in semantics])
+        prompt_length = len(encoded)
+        num_codebooks = (
+            len(semantics[0]) if self.num_codebooks is None else self.num_codebooks
+        )
+
+        # Pack the tokens and semantics (add <s> and </s> to semantic tokens)
+        tokens = (
+            encoded
+            + [self.semantic_token_id] * semantic_length
+            + self.tokenizer.convert_tokens_to_ids(["<|im_end|>"])
+        )
+
+        # Codebook bos/padding: 0, eos: 1
+        codes = [[CODEBOOK_PAD_TOKEN_ID] * prompt_length for _ in range(num_codebooks)]
+        for segment in semantics:
+            for book_idx, book in zip(range(num_codebooks), segment):
+                for j in book.values:
+                    codes[book_idx].append(int(j) + 1)
+
+        for book in codes:
+            book.extend([CODEBOOK_PAD_TOKEN_ID] * 1)
+
+        tokens = [tokens] + codes
+
+        tokens = torch.tensor(tokens, dtype=torch.long)
+        labels = tokens.clone()
+
+        if skip_text:
+            # If text is not provided, the sentence is used for condition only, all labels are -100
+            torch.fill_(labels, -100)
+            return tokens, labels
+
+        # Mask out the <s> tokens for semantic, predict semantic tokens only
+        # Since we don't mask out the input tokens, the language modeling still works
+        labels[1:, :prompt_length] = -100
+
+        tokens = tokens[:, :-1]
+        labels = labels[:, 1:]
+
+        # Verify the padding is correct, and the last token is eos
+        assert (tokens[1:, :prompt_length] == CODEBOOK_PAD_TOKEN_ID).all()
+        assert (labels[1:, -1:] == CODEBOOK_PAD_TOKEN_ID).all()
+
+        return tokens, labels
+
+
+@dataclass
+class TextDataCollator:
+    tokenizer: AutoTokenizer
+    max_length: int = 1024
+
+    def __call__(self, examples):
+        if "negative_tokens" in examples:
+            positive_examples = []
+            negative_examples = []
+
+            for i in examples:
+                positive_examples.append(
+                    {
+                        "tokens": i["tokens"],
+                        "labels": i["labels"],
+                    }
+                )
+                negative_examples.append(
+                    {
+                        "tokens": i["negative_tokens"],
+                        "labels": i["negative_labels"],
+                    }
+                )
+
+            examples = positive_examples + negative_examples
+
+        return self.batchify(examples)
+
+    def batchify(self, examples, tokens_key="tokens", labels_key="labels"):
+        tokens, attention_masks, labels = [], [], []
+
+        # Calculate the max length
+        max_tokens_length = 0
+        for example in examples:
+            max_tokens_length = max(max_tokens_length, example[tokens_key].size(1))
+        max_tokens_length = min(max_tokens_length, self.max_length)
+
+        for example in examples:
+            _tokens = example[tokens_key][:, :max_tokens_length]
+            _labels = example[labels_key][:, :max_tokens_length]
+            _attention_mask = torch.ones((max_tokens_length,), dtype=torch.bool)
+            tokens_length = _tokens.size(1)
+            _attention_mask[:tokens_length] = False
+
+            assert tokens_length == _labels.size(
+                1
+            ), f"{tokens_length} != {_labels.size(1)}"
+
+            if tokens_length < max_tokens_length:
+                _tokens = F.pad(
+                    _tokens,
+                    (0, max_tokens_length - tokens_length),
+                    value=self.tokenizer.eos_token_id,
+                )
+                _tokens[1:, tokens_length:] = CODEBOOK_PAD_TOKEN_ID
+                _labels = F.pad(
+                    _labels, (0, max_tokens_length - _labels.size(1)), value=-100
+                )
+
+            tokens.append(_tokens)
+            attention_masks.append(_attention_mask)
+            labels.append(_labels)
+
+        tokens = torch.stack(tokens, dim=0)
+        attention_masks = torch.stack(attention_masks, dim=0)
+        labels = torch.stack(labels, dim=0)
+
+        return {
+            "inputs": tokens,
+            "attention_masks": attention_masks,
+            "labels": labels,
+        }
+
+
+class InterleaveDataset(IterableDataset):
+    def __init__(
+        self,
+        datasets: list[IterableDataset],
+        probabilities: list[float],
+        seed: int = 42,
+    ):
+        super().__init__()
+
+        self.datasets = datasets
+        self.probabilities = probabilities
+        self.seed = seed
+
+    def __iter__(self):
+        rng = np.random.default_rng(self.seed)
+        dataset_iterators = [iter(dataset) for dataset in self.datasets]
+
+        while True:
+            # Random choice one
+            dataset_idx = rng.choice(len(self.datasets), p=self.probabilities)
+            dataset_iterator = dataset_iterators[dataset_idx]
+
+            try:
+                yield next(dataset_iterator)
+            except StopIteration:
+                # Exhausted, create a new iterator
+                dataset_iterators[dataset_idx] = iter(self.datasets[dataset_idx])
+                yield next(dataset_iterators[dataset_idx])
+
+
+class SemanticDataModule(LightningDataModule):
+    def __init__(
+        self,
+        train_dataset: Union[AutoTextSemanticInstructionDataset, InterleaveDataset],
+        val_dataset: Union[AutoTextSemanticInstructionDataset, InterleaveDataset],
+        batch_size: int = 32,
+        tokenizer: AutoTokenizer = None,
+        max_length: int = 1024,
+        num_workers: int = 4,
+    ):
+        super().__init__()
+
+        self.train_dataset = train_dataset
+        self.val_dataset = val_dataset
+        self.batch_size = batch_size
+        self.tokenizer = tokenizer
+        self.max_length = max_length
+        self.num_workers = num_workers
+
+    def train_dataloader(self):
+        return DataLoader(
+            self.train_dataset,
+            batch_size=self.batch_size,
+            collate_fn=TextDataCollator(self.tokenizer, self.max_length),
+            num_workers=self.num_workers,
+            persistent_workers=True,
+        )
+
+    def val_dataloader(self):
+        return DataLoader(
+            self.val_dataset,
+            batch_size=self.batch_size,
+            collate_fn=TextDataCollator(self.tokenizer, self.max_length),
+            num_workers=self.num_workers,
+            persistent_workers=True,
+        )
+
+
+if __name__ == "__main__":
+    from tqdm import tqdm
+
+    ds = AutoTextSemanticInstructionDataset(
+        ["data/protos"],
+        tokenizer=AutoTokenizer.from_pretrained("fishaudio/fish-speech-1"),
+        use_speaker=False,
+        interactive_prob=1.0,
+        skip_text_prob=0.5,
+    )
+
+    for i in ds:
+        print(ds.tokenizer.decode(i["tokens"][0], skip_special_tokens=False))
+        # i["labels"][0][i["labels"][0] == -100] = 0
+        # print(ds.tokenizer.decode(i["labels"][0], skip_special_tokens=False))
+        break

fish_speech/datasets/vqgan.py

@@ -0,0 +1,147 @@
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Optional
+
+import librosa
+import numpy as np
+import torch
+from lightning import LightningDataModule
+from torch.utils.data import DataLoader, Dataset
+
+from fish_speech.utils import RankedLogger
+
+logger = RankedLogger(__name__, rank_zero_only=False)
+
+
+class VQGANDataset(Dataset):
+    def __init__(
+        self,
+        filelist: str,
+        sample_rate: int = 32000,
+        hop_length: int = 640,
+        slice_frames: Optional[int] = None,
+    ):
+        super().__init__()
+
+        filelist = Path(filelist)
+        root = filelist.parent
+
+        self.files = [
+            root / line.strip()
+            for line in filelist.read_text(encoding="utf-8").splitlines()
+            if line.strip()
+        ]
+        self.sample_rate = sample_rate
+        self.hop_length = hop_length
+        self.slice_frames = slice_frames
+
+    def __len__(self):
+        return len(self.files)
+
+    def get_item(self, idx):
+        file = self.files[idx]
+
+        audio, _ = librosa.load(file, sr=self.sample_rate, mono=True)
+
+        # Slice audio and features
+        if (
+            self.slice_frames is not None
+            and audio.shape[0] > self.slice_frames * self.hop_length
+        ):
+            start = np.random.randint(
+                0, audio.shape[0] - self.slice_frames * self.hop_length
+            )
+            audio = audio[start : start + self.slice_frames * self.hop_length]
+
+        if len(audio) == 0:
+            return None
+
+        max_value = np.abs(audio).max()
+        if max_value > 1.0:
+            audio = audio / max_value
+
+        return {
+            "audio": torch.from_numpy(audio),
+        }
+
+    def __getitem__(self, idx):
+        try:
+            return self.get_item(idx)
+        except Exception as e:
+            import traceback
+
+            traceback.print_exc()
+            logger.error(f"Error loading {self.files[idx]}: {e}")
+            return None
+
+
+@dataclass
+class VQGANCollator:
+    def __call__(self, batch):
+        batch = [x for x in batch if x is not None]
+
+        audio_lengths = torch.tensor([len(x["audio"]) for x in batch])
+        audio_maxlen = audio_lengths.max()
+
+        # Rounds up to nearest multiple of 2 (audio_lengths)
+        audios = []
+        for x in batch:
+            audios.append(
+                torch.nn.functional.pad(x["audio"], (0, audio_maxlen - len(x["audio"])))
+            )
+
+        return {
+            "audios": torch.stack(audios),
+            "audio_lengths": audio_lengths,
+        }
+
+
+class VQGANDataModule(LightningDataModule):
+    def __init__(
+        self,
+        train_dataset: VQGANDataset,
+        val_dataset: VQGANDataset,
+        batch_size: int = 32,
+        num_workers: int = 4,
+        val_batch_size: Optional[int] = None,
+    ):
+        super().__init__()
+
+        self.train_dataset = train_dataset
+        self.val_dataset = val_dataset
+        self.batch_size = batch_size
+        self.val_batch_size = val_batch_size or batch_size
+        self.num_workers = num_workers
+
+    def train_dataloader(self):
+        return DataLoader(
+            self.train_dataset,
+            batch_size=self.batch_size,
+            collate_fn=VQGANCollator(),
+            num_workers=self.num_workers,
+            shuffle=True,
+            persistent_workers=True,
+        )
+
+    def val_dataloader(self):
+        return DataLoader(
+            self.val_dataset,
+            batch_size=self.val_batch_size,
+            collate_fn=VQGANCollator(),
+            num_workers=self.num_workers,
+            persistent_workers=True,
+        )
+
+
+if __name__ == "__main__":
+    dataset = VQGANDataset("data/LibriTTS_R/vq_train_filelist.txt")
+    dataloader = DataLoader(
+        dataset, batch_size=4, shuffle=False, collate_fn=VQGANCollator()
+    )
+
+    for batch in dataloader:
+        print(batch["audios"].shape)
+        print(batch["features"].shape)
+        print(batch["audio_lengths"])
+        print(batch["feature_lengths"])
+        break

fish_speech/i18n/README.md

@@ -0,0 +1,27 @@
+## i18n Folder Attribution
+
+The `i18n` folder within the `fish_speech` directory contains files initially sourced from the RVC project. In compliance with the MIT license under which these files were released, we acknowledge the original authors and sources below:
+
+### fish_speech/i18n/core.py
+
+**Related code from RVC:**
+[https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/83d6a64e675d9bbd6e92ee450c5f807ed2bb54d8/i18n/i18n.py](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/83d6a64e675d9bbd6e92ee450c5f807ed2bb54d8/i18n/i18n.py)
+
+**Initial commit:**
+add localization(添加本地化) [RVC-Project/Retrieval-based-Voice-Conversion-WebUI#35](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/pull/35)
+
+**Initial author:**
+[@L4Ph](https://github.com/L4Ph)
+
+### fish_speech/i18n/scan.py
+
+**Related code from RVC:**
+[https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/83d6a64e675d9bbd6e92ee450c5f807ed2bb54d8/i18n/scan_i18n.py](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/83d6a64e675d9bbd6e92ee450c5f807ed2bb54d8/i18n/scan_i18n.py)
+
+**Initial commit:**
+File for detecting i18n missing keys [RVC-Project/Retrieval-based-Voice-Conversion-WebUI#1058](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/pull/1058)
+
+**Initial author:**
+[@towzeur](https://github.com/towzeur)
+
+We appreciate the contributions of the RVC project and its authors.

fish_speech/i18n/__init__.py

@@ -0,0 +1,3 @@
+from .core import i18n
+
+__all__ = ["i18n"]

fish_speech/i18n/core.py

@@ -0,0 +1,40 @@
+import json
+import locale
+from pathlib import Path
+
+I18N_FILE_PATH = Path(__file__).parent / "locale"
+DEFAULT_LANGUAGE = "en_US"
+
+
+def load_language_list(language):
+    with open(I18N_FILE_PATH / f"{language}.json", "r", encoding="utf-8") as f:
+        language_list = json.load(f)
+
+    return language_list
+
+
+class I18nAuto:
+    def __init__(self):
+        i18n_file = Path(".locale")
+
+        if i18n_file.exists():
+            with open(i18n_file, "r", encoding="utf-8") as f:
+                language = f.read().strip()
+        else:
+            # getlocale can't identify the system's language ((None, None))
+            language = locale.getdefaultlocale()[0]
+
+        if (I18N_FILE_PATH / f"{language}.json").exists() is False:
+            language = DEFAULT_LANGUAGE
+
+        self.language = language
+        self.language_map = load_language_list(language)
+
+    def __call__(self, key):
+        return self.language_map.get(key, key)
+
+    def __repr__(self):
+        return "Use Language: " + self.language
+
+
+i18n = I18nAuto()

fish_speech/i18n/locale/en_US.json

@@ -0,0 +1,122 @@
+{
+  "16-mixed is recommended for 10+ series GPU": "16-mixed is recommended for 10+ series GPU",
+  "5 to 10 seconds of reference audio, useful for specifying speaker.": "5 to 10 seconds of reference audio, useful for specifying speaker.",
+  "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).",
+  "Accumulate Gradient Batches": "Accumulate Gradient Batches",
+  "Add to Processing Area": "Add to Processing Area",
+  "Added path successfully!": "Added path successfully!",
+  "Advanced Config": "Advanced Config",
+  "Base LLAMA Model": "Base LLAMA Model",
+  "Batch Inference": "Batch Inference",
+  "Batch Size": "Batch Size",
+  "Changing with the Model Path": "Changing with the Model Path",
+  "Chinese": "Chinese",
+  "Compile Model": "Compile Model",
+  "Compile the model can significantly reduce the inference time, but will increase cold start time": "Compile the model can significantly reduce the inference time, but will increase cold start time",
+  "Copy": "Copy",
+  "Data Preprocessing": "Data Preprocessing",
+  "Data Preprocessing Path": "Data Preprocessing Path",
+  "Data Source": "Data Source",
+  "Decoder Model Config": "Decoder Model Config",
+  "Decoder Model Path": "Decoder Model Path",
+  "Disabled": "Disabled",
+  "Enable Reference Audio": "Enable Reference Audio",
+  "English": "English",
+  "Error Message": "Error Message",
+  "File Preprocessing": "File Preprocessing",
+  "Generate": "Generate",
+  "Generated Audio": "Generated Audio",
+  "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format",
+  "Infer interface is closed": "Infer interface is closed",
+  "Inference Configuration": "Inference Configuration",
+  "Inference Server Configuration": "Inference Server Configuration",
+  "Inference Server Error": "Inference Server Error",
+  "Inferring interface is launched at {}": "Inferring interface is launched at {}",
+  "Initial Learning Rate": "Initial Learning Rate",
+  "Input Audio & Source Path for Transcription": "Input Audio & Source Path for Transcription",
+  "Input Text": "Input Text",
+  "Invalid path: {}": "Invalid path: {}",
+  "It is recommended to use CUDA, if you have low configuration, use CPU": "It is recommended to use CUDA, if you have low configuration, use CPU",
+  "Iterative Prompt Length, 0 means off": "Iterative Prompt Length, 0 means off",
+  "Japanese": "Japanese",
+  "LLAMA Configuration": "LLAMA Configuration",
+  "LLAMA Model Config": "LLAMA Model Config",
+  "LLAMA Model Path": "LLAMA Model Path",
+  "Labeling Device": "Labeling Device",
+  "LoRA Model to be merged": "LoRA Model to be merged",
+  "Maximum Audio Duration": "Maximum Audio Duration",
+  "Maximum Length per Sample": "Maximum Length per Sample",
+  "Maximum Training Steps": "Maximum Training Steps",
+  "Maximum tokens per batch, 0 means no limit": "Maximum tokens per batch, 0 means no limit",
+  "Merge": "Merge",
+  "Merge LoRA": "Merge LoRA",
+  "Merge successfully": "Merge successfully",
+  "Minimum Audio Duration": "Minimum Audio Duration",
+  "Model Output Path": "Model Output Path",
+  "Model Size": "Model Size",
+  "Move": "Move",
+  "Move files successfully": "Move files successfully",
+  "No audio generated, please check the input text.": "No audio generated, please check the input text.",
+  "No selected options": "No selected options",
+  "Number of Workers": "Number of Workers",
+  "Open Inference Server": "Open Inference Server",
+  "Open Labeler WebUI": "Open Labeler WebUI",
+  "Open Tensorboard": "Open Tensorboard",
+  "Opened labeler in browser": "Opened labeler in browser",
+  "Optional Label Language": "Optional Label Language",
+  "Optional online ver": "Optional online ver",
+  "Output Path": "Output Path",
+  "Path error, please check the model file exists in the corresponding path": "Path error, please check the model file exists in the corresponding path",
+  "Precision": "Precision",
+  "Probability of applying Speaker Condition": "Probability of applying Speaker Condition",
+  "Put your text here.": "Put your text here.",
+  "Reference Audio": "Reference Audio",
+  "Reference Text": "Reference Text",
+  "Related code and weights are released under CC BY-NC-SA 4.0 License.": "Related code and weights are released under CC BY-NC-SA 4.0 License.",
+  "Remove Selected Data": "Remove Selected Data",
+  "Removed path successfully!": "Removed path successfully!",
+  "Repetition Penalty": "Repetition Penalty",
+  "Save model every n steps": "Save model every n steps",
+  "Select LLAMA ckpt": "Select LLAMA ckpt",
+  "Select VITS ckpt": "Select VITS ckpt",
+  "Select VQGAN ckpt": "Select VQGAN ckpt",
+  "Select source file processing method": "Select source file processing method",
+  "Select the model to be trained (Depending on the Tab page you are on)": "Select the model to be trained (Depending on the Tab page you are on)",
+  "Selected: {}": "Selected: {}",
+  "Speaker": "Speaker",
+  "Speaker is identified by the folder name": "Speaker is identified by the folder name",
+  "Start Training": "Start Training",
+  "Streaming Audio": "Streaming Audio",
+  "Streaming Generate": "Streaming Generate",
+  "Tensorboard Host": "Tensorboard Host",
+  "Tensorboard Log Path": "Tensorboard Log Path",
+  "Tensorboard Port": "Tensorboard Port",
+  "Tensorboard interface is closed": "Tensorboard interface is closed",
+  "Tensorboard interface is launched at {}": "Tensorboard interface is launched at {}",
+  "Text is too long, please keep it under {} characters.": "Text is too long, please keep it under {} characters.",
+  "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.",
+  "Training Configuration": "Training Configuration",
+  "Training Error": "Training Error",
+  "Training stopped": "Training stopped",
+  "Type name of the speaker": "Type name of the speaker",
+  "Type the path or select from the dropdown": "Type the path or select from the dropdown",
+  "Use LoRA": "Use LoRA",
+  "Use LoRA can save GPU memory, but may reduce the quality of the model": "Use LoRA can save GPU memory, but may reduce the quality of the model",
+  "Use filelist": "Use filelist",
+  "Use large for 10G+ GPU, medium for 5G, small for 2G": "Use large for 10G+ GPU, medium for 5G, small for 2G",
+  "VITS Configuration": "VITS Configuration",
+  "VQGAN Configuration": "VQGAN Configuration",
+  "Validation Batch Size": "Validation Batch Size",
+  "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "View the status of the preprocessing folder (use the slider to control the depth of the tree)",
+  "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.",
+  "WebUI Host": "WebUI Host",
+  "WebUI Port": "WebUI Port",
+  "Whisper Model": "Whisper Model",
+  "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).",
+  "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU",
+  "latest": "latest",
+  "new": "new",
+  "Realtime Transform Text": "Realtime Transform Text",
+  "Normalization Result Preview (Currently Only Chinese)": "Normalization Result Preview (Currently Only Chinese)",
+  "Text Normalization": "Text Normalization"
+}

fish_speech/i18n/locale/es_ES.json

@@ -0,0 +1,122 @@
+{
+  "16-mixed is recommended for 10+ series GPU": "se recomienda 16-mixed para GPU de la serie 10+",
+  "5 to 10 seconds of reference audio, useful for specifying speaker.": "5 a 10 segundos de audio de referencia, útil para especificar el hablante.",
+  "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "Un modelo de texto a voz basado en VQ-GAN y Llama desarrollado por [Fish Audio](https://fish.audio).",
+  "Accumulate Gradient Batches": "Acumular lotes de gradientes",
+  "Add to Processing Area": "Agregar al Área de Procesamiento",
+  "Added path successfully!": "¡Ruta agregada exitosamente!",
+  "Advanced Config": "Configuración Avanzada",
+  "Base LLAMA Model": "Modelo Base LLAMA",
+  "Batch Inference": "Inferencia por Lote",
+  "Batch Size": "Tamaño del Lote",
+  "Changing with the Model Path": "Cambiando con la Ruta del Modelo",
+  "Chinese": "Chino",
+  "Compile Model": "Compilar Modelo",
+  "Compile the model can significantly reduce the inference time, but will increase cold start time": "Compilar el modelo puede reducir significativamente el tiempo de inferencia, pero aumentará el tiempo de inicio en frío",
+  "Copy": "Copiar",
+  "Data Preprocessing": "Preprocesamiento de Datos",
+  "Data Preprocessing Path": "Ruta de Preprocesamiento de Datos",
+  "Data Source": "Fuente de Datos",
+  "Decoder Model Config": "Configuración del modelo decodificador",
+  "Decoder Model Path": "Ruta del modelo decodificador",
+  "Disabled": "Desactivado",
+  "Enable Reference Audio": "Habilitar Audio de Referencia",
+  "English": "Inglés",
+  "Error Message": "Mensaje de Error",
+  "File Preprocessing": "Preprocesamiento de Archivos",
+  "Generate": "Generar",
+  "Generated Audio": "Audio Generado",
+  "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "Si no hay texto correspondiente para el audio, aplique ASR para asistencia, soporte para formato .txt o .lab",
+  "Infer interface is closed": "La interfaz de inferencia está cerrada",
+  "Inference Configuration": "Configuración de Inferencia",
+  "Inference Server Configuration": "Configuración del Servidor de Inferencia",
+  "Inference Server Error": "Error del Servidor de Inferencia",
+  "Inferring interface is launched at {}": "La interfaz de inferencia se ha lanzado en {}",
+  "Initial Learning Rate": "Tasa de Aprendizaje Inicial",
+  "Input Audio & Source Path for Transcription": "Audio de Entrada y Ruta de Origen para Transcripción",
+  "Input Text": "Texto de Entrada",
+  "Invalid path: {}": "Ruta inválida: {}",
+  "It is recommended to use CUDA, if you have low configuration, use CPU": "Se recomienda usar CUDA, si tiene una configuración baja, use CPU",
+  "Iterative Prompt Length, 0 means off": "Longitud de la Indicación Iterativa, 0 significa apagado",
+  "Japanese": "Japonés",
+  "LLAMA Configuration": "Configuración de LLAMA",
+  "LLAMA Model Config": "Configuración del Modelo LLAMA",
+  "LLAMA Model Path": "Ruta del Modelo LLAMA",
+  "Labeling Device": "Dispositivo de Etiquetado",
+  "LoRA Model to be merged": "Modelo LoRA a fusionar",
+  "Maximum Audio Duration": "Duración máxima de audio",
+  "Maximum Length per Sample": "Longitud Máxima por Muestra",
+  "Maximum Training Steps": "Pasos Máximos de Entrenamiento",
+  "Maximum tokens per batch, 0 means no limit": "Máximo de tokens por lote, 0 significa sin límite",
+  "Merge": "Fusionar",
+  "Merge LoRA": "Fusionar LoRA",
+  "Merge successfully": "Fusionado exitosamente",
+  "Minimum Audio Duration": "Duración mínima de audio",
+  "Model Output Path": "Ruta de Salida del Modelo",
+  "Model Size": "Tamaño del Modelo",
+  "Move": "Mover",
+  "Move files successfully": "Archivos movidos exitosamente",
+  "No audio generated, please check the input text.": "No se generó audio, por favor verifique el texto de entrada.",
+  "No selected options": "No hay opciones seleccionadas",
+  "Number of Workers": "Número de Trabajadores",
+  "Open Inference Server": "Abrir Servidor de Inferencia",
+  "Open Labeler WebUI": "Abrir Interfaz Web del Etiquetador",
+  "Open Tensorboard": "Abrir Tensorboard",
+  "Opened labeler in browser": "Se abrió el etiquetador en el navegador",
+  "Optional Label Language": "Idioma de Etiquetado Opcional",
+  "Optional online ver": "Ver en línea opcional",
+  "Output Path": "Ruta de Salida",
+  "Path error, please check the model file exists in the corresponding path": "Error de ruta, por favor verifique que el archivo del modelo exista en la ruta correspondiente",
+  "Precision": "Precisión",
+  "Probability of applying Speaker Condition": "Probabilidad de aplicar Condición de Hablante",
+  "Put your text here.": "Ponga su texto aquí.",
+  "Reference Audio": "Audio de Referencia",
+  "Reference Text": "Texto de Referencia",
+  "Related code and weights are released under CC BY-NC-SA 4.0 License.": "El código relacionado y los pesos se publican bajo la Licencia CC BY-NC-SA 4.0.",
+  "Remove Selected Data": "Eliminar Datos Seleccionados",
+  "Removed path successfully!": "¡Ruta eliminada exitosamente!",
+  "Repetition Penalty": "Penalización por Repetición",
+  "Save model every n steps": "Guardar modelo cada n pasos",
+  "Select LLAMA ckpt": "Seleccionar punto de control LLAMA",
+  "Select VITS ckpt": "Seleccionar punto de control VITS",
+  "Select VQGAN ckpt": "Seleccionar punto de control VQGAN",
+  "Select source file processing method": "Seleccione el método de procesamiento de archivos fuente",
+  "Select the model to be trained (Depending on the Tab page you are on)": "Seleccione el modelo a entrenar (Dependiendo de la pestaña en la que se encuentre)",
+  "Selected: {}": "Seleccionado: {}",
+  "Speaker": "Hablante",
+  "Speaker is identified by the folder name": "El hablante se identifica por el nombre de la carpeta",
+  "Start Training": "Iniciar Entrenamiento",
+  "Streaming Audio": "transmisión de audio",
+  "Streaming Generate": "síntesis en flujo",
+  "Tensorboard Host": "Host de Tensorboard",
+  "Tensorboard Log Path": "Ruta de Registro de Tensorboard",
+  "Tensorboard Port": "Puerto de Tensorboard",
+  "Tensorboard interface is closed": "La interfaz de Tensorboard está cerrada",
+  "Tensorboard interface is launched at {}": "La interfaz de Tensorboard se ha lanzado en {}",
+  "Text is too long, please keep it under {} characters.": "El texto es demasiado largo, por favor manténgalo por debajo de {} caracteres.",
+  "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "La ruta de la carpeta de entrada a la izquierda o la lista de archivos. Ya sea que esté marcado o no, se utilizará para el entrenamiento posterior en esta lista.",
+  "Training Configuration": "Configuración de Entrenamiento",
+  "Training Error": "Error de Entrenamiento",
+  "Training stopped": "Entrenamiento detenido",
+  "Type name of the speaker": "Escriba el nombre del hablante",
+  "Type the path or select from the dropdown": "Escriba la ruta o seleccione de la lista desplegable",
+  "Use LoRA": "Usar LoRA",
+  "Use LoRA can save GPU memory, but may reduce the quality of the model": "Usar LoRA puede ahorrar memoria GPU, pero puede reducir la calidad del modelo",
+  "Use filelist": "Usar lista de archivos",
+  "Use large for 10G+ GPU, medium for 5G, small for 2G": "Use grande para GPU de 10G+, mediano para 5G, pequeño para 2G",
+  "VITS Configuration": "Configuración de VITS",
+  "VQGAN Configuration": "Configuración de VQGAN",
+  "Validation Batch Size": "Tamaño del Lote de Validación",
+  "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "Vea el estado de la carpeta de preprocesamiento (use el control deslizante para controlar la profundidad del árbol)",
+  "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "No somos responsables de ningún mal uso del modelo, por favor considere sus leyes y regulaciones locales antes de usarlo.",
+  "WebUI Host": "Host de WebUI",
+  "WebUI Port": "Puerto de WebUI",
+  "Whisper Model": "Modelo Whisper",
+  "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "Puede encontrar el código fuente [aquí](https://github.com/fishaudio/fish-speech) y los modelos [aquí](https://huggingface.co/fishaudio/fish-speech-1).",
+  "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "Se recomienda bf16-true para GPU de la serie 30+, se recomienda 16-mixed para GPU de la serie 10+",
+  "latest": "más reciente",
+  "new": "nuevo",
+  "Realtime Transform Text": "Transformación de Texto en Tiempo Real",
+  "Normalization Result Preview (Currently Only Chinese)": "Vista Previa del Resultado de Normalización (Actualmente Solo Chino)",
+  "Text Normalization": "Normalización de Texto"
+}

fish_speech/i18n/locale/ja_JP.json

@@ -0,0 +1,123 @@
+{
+  "16-mixed is recommended for 10+ series GPU": "10シリーズ以降のGPUには16-mixedをお勧めします",
+  "5 to 10 seconds of reference audio, useful for specifying speaker.": "話者を指定するのに役立つ、5～10秒のリファレンスオーディオ。",
+  "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "[Fish Audio](https://fish.audio)が開発したVQ-GANとLlamaに基づくテキスト音声合成モデル。",
+  "Accumulate Gradient Batches": "勾配バッチの累積",
+  "Add to Processing Area": "処理エリアに追加",
+  "Added path successfully!": "パスの追加に成功しました！",
+  "Advanced Config": "詳細設定",
+  "Base LLAMA Model": "基本LLAMAモデル",
+  "Batch Inference": "バッチ推論",
+  "Batch Size": "バッチサイズ",
+  "Changing with the Model Path": "モデルのパスに伴って変化する",
+  "Chinese": "中国語",
+  "Compile Model": "モデルのコンパイル",
+  "Compile the model can significantly reduce the inference time, but will increase cold start time": "モデルをコンパイルすると推論時間を大幅に短縮できますが、コールドスタート時間が長くなります",
+  "Copy": "コピー",
+  "Data Preprocessing": "データ前処理",
+  "Data Preprocessing Path": "データ前処理パス",
+  "Data Source": "データソース",
+  "Decoder Model Config": "デコーダーモデルの構成",
+  "Decoder Model Path": "デコーダーモデルのパス",
+  "Disabled": "無効",
+  "Enable Reference Audio": "リファレンスオーディオを有効にする",
+  "English": "英語",
+  "Error Message": "エラーメッセージ",
+  "File Preprocessing": "文書前处理",
+  "Generate": "生成",
+  "Generated Audio": "生成されたオーディオ",
+  "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "音声に対応するテキストがない場合は、ASRを適用してサポートします。.txtまたは.lab形式をサポートしています",
+  "Infer interface is closed": "推論インターフェースが閉じられています",
+  "Inference Configuration": "推論設定",
+  "Inference Server Configuration": "推論サーバー設定",
+  "Inference Server Error": "推論サーバーエラー",
+  "Inferring interface is launched at {}": "推論インターフェースが{}で起動しました",
+  "Initial Learning Rate": "初期学習率",
+  "Input Audio & Source Path for Transcription": "入力オーディオと文字起こしのソースパス",
+  "Input Text": "入力テキスト",
+  "Invalid path: {}": "無効なパス: {}",
+  "It is recommended to use CUDA, if you have low configuration, use CPU": "CUDAの使用をお勧めします。低い構成の場合はCPUを使用してください",
+  "Iterative Prompt Length, 0 means off": "反復プロンプト長。0はオフを意味します",
+  "Japanese": "日本語",
+  "LLAMA Configuration": "LLAMA設定",
+  "LLAMA Model Config": "LLAMAモデル設定",
+  "LLAMA Model Path": "LLAMAモデルパス",
+  "Labeling Device": "ラベリングデバイス",
+  "LoRA Model to be merged": "マージするLoRAモデル",
+  "Maximum Audio Duration": "最大オーディオの長さ",
+  "Maximum Length per Sample": "サンプルあたりの最大長",
+  "Maximum Training Steps": "最大トレーニングステップ数",
+  "Maximum tokens per batch, 0 means no limit": "バッチあたりの最大トークン数。0は制限なしを意味します",
+  "Merge": "マージ",
+  "Merge LoRA": "LoRAのマージ",
+  "Merge successfully": "マージに成功しました",
+  "Minimum Audio Duration": "最小オーディオの長さ",
+  "Model Output Path": "モデル出力パス",
+  "Model Size": "モデルサイズ",
+  "Move": "移動",
+  "Move files successfully": "ファイルの移動に成功しました",
+  "No audio generated, please check the input text.": "オーディオが生成されていません。入力テキストを確認してください。",
+  "No selected options": "選択されたオプションはありません",
+  "Number of Workers": "ワーカー数",
+  "Open Inference Server": "推論サーバーを開く",
+  "Open Labeler WebUI": "ラベラーWebUIを開く",
+  "Open Tensorboard": "Tensorboardを開く",
+  "Opened labeler in browser": "ブラウザでラベラーを開きました",
+  "Optional Label Language": "オプションのラベル言語",
+  "Optional online ver": "オプションのオンラインバージョン",
+  "Output Path": "出力パス",
+  "Path error, please check the model file exists in the corresponding path": "パスエラー。対応するパスにモデルファイルが存在するか確認してください",
+  "Precision": "精度",
+  "Probability of applying Speaker Condition": "話者条件を適用する確率",
+  "Put your text here.": "ここにテキストを入力してください。",
+  "Reference Audio": "リファレンスオーディオ",
+  "Reference Text": "リファレンステキスト",
+  "Related code and weights are released under CC BY-NC-SA 4.0 License.": "関連コードと重みはCC BY-NC-SA 4.0ライセンスの下でリリースされます。",
+  "Remove Selected Data": "選択したデータを削除",
+  "Removed path successfully!": "パスの削除に成功しました！",
+  "Repetition Penalty": "反復ペナルティ",
+  "Save model every n steps": "nステップごとにモデルを保存",
+  "Select LLAMA ckpt": " LLAMA チェックポイントを選択",
+  "Select VITS ckpt": "VITS チェックポイントを選択",
+  "Select VQGAN ckpt": "VQGAN チェックポイントを選択",
+  "Select source file processing method": "ソースファイルの処理方法を選択",
+  "Select the model to be trained (Depending on the Tab page you are on)": "タブページに応じてトレーニングするモデルを選択してください",
+  "Selected: {}": "選択済み: {}",
+  "Speaker": "話者",
+  "Speaker is identified by the folder name": "話者はフォルダ名で識別されます",
+  "Start Training": "トレーニング開始",
+  "Streaming Audio": "ストリーミングオーディオ",
+  "Streaming Generate": "ストリーミング合成",
+  "Tensorboard Host": "Tensorboardホスト",
+  "Tensorboard Log Path": "Tensorboardログパス",
+  "Tensorboard Port": "Tensorboardポート",
+  "Tensorboard interface is closed": "Tensorboardインターフェースが閉じられています",
+  "Tensorboard interface is launched at {}": "Tensorboardインターフェースが{}で起動されました",
+  "Text is too long, please keep it under {} characters.": "テキストが長すぎます。{}文字以内に抑えてください。",
+  "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "左側の入力フォルダまたはファイルリストのパス。チェックの有無にかかわらず、このリストの後続のトレーニングに使用されます。",
+  "Training Configuration": "トレーニング設定",
+  "Training Error": "トレーニングエラー",
+  "Training stopped": "トレーニングが停止しました",
+  "Type name of the speaker": "話者の名前を入力",
+  "Type the path or select from the dropdown": "パスを入力するか、ドロップダウンから選択してください",
+  "Use LoRA": "LoRAを使用",
+  "Use LoRA can save GPU memory, but may reduce the quality of the model": "LoRAを使用するとGPUメモリを節約できますが、モデルの品質が低下する可能性があります",
+  "Use filelist": "ファイルリストを使用",
+  "Use large for 10G+ GPU, medium for 5G, small for 2G": "10G以上のGPUには大、5Gには中、2Gには小を使用してください",
+  "VITS Configuration": "VITS の構成",
+  "VQGAN Configuration": "VQGAN の構成",
+  "Validation Batch Size": "検証バッチサイズ",
+  "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "前処理フォルダの状態を表示（スライダーを使用してツリーの深さを制御）",
+  "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "モデルの誤用については一切責任を負いません。使用する前に、現地の法律と規制を考慮してください。",
+  "WebUI Host": "WebUIホスト",
+  "WebUI Port": "WebUIポート",
+  "Whisper Model": "Whisperモデル",
+  "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "ソースコードは[こちら](https://github.com/fishaudio/fish-speech)、モデルは[こちら](https://huggingface.co/fishaudio/fish-speech-1)にあります。",
+  "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "30シリーズ以降のGPUにはbf16-trueを、10シリーズ以降のGPUには16-mixedをお勧めします",
+  "latest": "最新",
+  "new": "新規",
+  "Realtime Transform Text": "リアルタイム変換テキスト",
+  "Normalization Result Preview (Currently Only Chinese)": "正規化結果プレビュー（現在は中国語のみ）",
+  "Text Normalization": "テキスト正規化"
+
+}

fish_speech/i18n/locale/pt_BR.json

@@ -0,0 +1,133 @@
+{
+  "5 to 10 seconds of reference audio, useful for specifying speaker.": "5 a 10 segundos de áudio de referência, útil para especificar o orador.",
+  "A text-to-speech model based on VQ-GAN and Llama developed by [Fish Audio](https://fish.audio).": "Um modelo de texto para fala baseado em VQ-GAN e Llama desenvolvido por [Fish Audio](https://fish.audio).",
+  "Accumulate Gradient Batches": "Acumular Lotes de Gradiente",
+  "Add to Processing Area": "Adicionar à Área de Processamento",
+  "Added path successfully!": "Caminho adicionado com sucesso!",
+  "Advanced Config": "Configuração Avançada",
+  "Base LLAMA Model": "Modelo LLAMA Base",
+  "Batch Inference": "Inferência em Lote",
+  "Batch Size": "Tamanho do Lote",
+  "Changing with the Model Path": "Alterando com o Caminho do Modelo",
+
+  "Compile Model": "Compilar Modelo",
+  "Compile the model can significantly reduce the inference time, but will increase cold start time": "Compilar o modelo pode reduzir significativamente o tempo de inferência, mas aumentará a latência inicial",
+  "Copy": "Copiar",
+  "Data Preprocessing": "Pré-processamento de Dados",
+  "Data Preprocessing Path": "Caminho de Pré-processamento de Dados",
+  "Data Source": "Fonte de Dados",
+  "Decoder Model Config": "Configuração do Modelo Decodificador",
+  "Decoder Model Path": "Caminho do Modelo Decodificador",
+  "Disabled": "Desativado",
+  "Enable Initial Prompt": "Habilitar Prompt Inicial",
+  "Enable Reference Audio": "Habilitar Áudio de Referência",
+  "English": "Inglês",
+  "Japanese": "Japonês",
+  "Chinese": "Chinês",
+  "Portuguese": "Português",
+  "Spanish": "Espanhol",
+  "Error Message": "Mensagem de Erro",
+  "Faster Whisper, Up to 5g GPU memory usage": "Faster Whisper (Usa até 5 GB de vRAM)",
+  "File Preprocessing": "Pré-processamento de Arquivos",
+  "Generate": "Gerar",
+  "Generated Audio": "Áudio Gerado",
+  "If there is no corresponding text for the audio, apply ASR for assistance, support .txt or .lab format": "Se não houver texto correspondente ao áudio, utilize o ASR para assistência (formatos .txt ou .lab)",
+  "Infer interface is closed": "A interface de inferência foi fechada",
+  "Inference Configuration": "Configuração de Inferência",
+  "Inference Server Configuration": "Configuração do Servidor de Inferência",
+  "Inference Server Error": "Erro do Servidor de Inferência",
+  "Inferring interface is launched at {}": "A interface de inferência foi iniciada em {}",
+  "Initial Learning Rate": "Taxa de Aprendizagem Inicial",
+  "Initial Prompt": "Prompt Inicial",
+  "Initial prompt can provide contextual or vocabulary-specific guidance to the model.": "O prompt inicial pode fornecer orientação contextual ou específica de vocabulário para o modelo.",
+  "Input Audio & Source Path for Transcription": "Entrada de Áudio/Caminho de Origem para Transcrição",
+  "Input Text": "Texto de Entrada",
+  "Invalid path: {}": "Caminho inválido: {}",
+  "It is recommended to use CUDA, if you have low configuration, use CPU": "Para GPUs Nvidia é recomendado usar CUDA. Se não tiver uma GPU Nvidia, use CPU",
+  "Iterative Prompt Length, 0 means off": "Comprimento do Prompt Iterativo (0 = desativado)",
+  "LLAMA Configuration": "Configuração do LLAMA",
+  "LLAMA Model Config": "Configuração do Modelo LLAMA",
+  "LLAMA Model Path": "Caminho do Modelo LLAMA",
+  "Labeling Device": "Dispositivo de Rotulagem",
+  "LoRA Model to be merged": "Modelo LoRA para mesclagem",
+  "Maximum Length per Sample": "Comprimento Máximo por Amostra",
+  "Maximum Training Steps": "Etapas Máximas de Treinamento",
+  "Maximum tokens per batch, 0 means no limit": "Número máximo de tokens por lote, 0 significa sem limite",
+  "Merge": "Mesclar",
+  "Merge LoRA": "Mesclar LoRA",
+  "Merge successfully": "Mesclado com sucesso",
+  "Model Output Path": "Caminho de Saída do Modelo",
+  "Model Quantization": "Quantização do Modelo",
+  "Model Size": "Tamanho do Modelo",
+  "Move": "Mover",
+  "Move files successfully": "Arquivos movidos com sucesso",
+  "No audio generated, please check the input text.": "Nenhum áudio gerado, verifique o texto de entrada.",
+  "No selected options": "Nenhuma opção selecionada",
+  "Normalization Result Preview (Currently Only Chinese)": "Pré-visualização do Resultado da Normalização (Atualmente Apenas Chinês)",
+  "Number of Workers": "Número de Processos",
+  "Open Inference Server": "Abrir Servidor de Inferência",
+  "Open Labeler WebUI": "Abrir WebUI de Rotulagem",
+  "Open Tensorboard": "Abrir Tensorboard",
+  "Opened labeler in browser": "WebUI de rotulagem aberta no navegador",
+  "Optional Label Language": "Idioma do Rótulo (Opcional)",
+  "Optional online ver": "Versão online (opcional)",
+  "Output Path": "Caminho de Saída",
+  "Path error, please check the model file exists in the corresponding path": "Erro de caminho, verifique se o arquivo do modelo existe no caminho correspondente",
+  "Post-quantification Precision": "Precisão Pós-quantização",
+  "Precision": "Precisão",
+  "Probability of applying Speaker Condition": "Probabilidade de Aplicar Condição de Orador",
+  "Put your text here.": "Insira seu texto aqui.",
+  "Quantify": "Quantizar",
+  "Quantify successfully": "Quantizado com sucesso",
+  "Realtime Transform Text": "Transformar Texto em Tempo Real",
+  "Reference Audio": "Áudio de Referência",
+  "Reference Text": "Texto de Referência",
+  "warning": "Aviso",
+  "Pre-processing begins...": "O pré-processamento começou!",
+  "Related code and weights are released under CC BY-NC-SA 4.0 License.": "O código relacionado e os pesos são licenciados sob a Licença CC BY-NC-SA 4.0.",
+  "Remove Selected Data": "Remover Dados Selecionados",
+  "Removed path successfully!": "Caminho removido com sucesso!",
+  "Repetition Penalty": "Penalidade de Repetição",
+  "Save model every n steps": "Salvar modelo a cada n etapas",
+  "Select LLAMA ckpt": "Selecionar .ckpt do LLAMA",
+  "Select source file processing method": "Escolha como processar o arquivo de origem",
+  "Select the model to be trained (Depending on the Tab page you are on)": "Selecione o modelo para o treinamento (dependendo da aba em que você está)",
+  "Selected: {}": "Selecionado: {}",
+  "Speaker is identified by the folder name": "O orador é identificado pelo nome da pasta",
+  "Start Training": "Iniciar Treinamento",
+  "Streaming Audio": "Áudio em Streaming",
+  "Streaming Generate": "Geração em Streaming",
+  "Tensorboard Host": "Host do Tensorboard",
+  "Tensorboard Log Path": "Caminho de Log do Tensorboard",
+  "Tensorboard Port": "Porta do Tensorboard",
+  "Tensorboard interface is closed": "A interface do Tensorboard está fechada",
+  "Tensorboard interface is launched at {}": "A interface do Tensorboard foi iniciada em {}",
+  "Text Normalization": "Normalização de Texto",
+  "Text is too long, please keep it under {} characters.": "O texto é muito longo. Mantenha-o com menos de {} caracteres.",
+  "The lower the quantitative precision, the more the effectiveness may decrease, but the greater the efficiency will increase": "Quanto menor a precisão quantitativa, mais a eficácia pode diminuir, mas maior será o aumento da eficiência",
+  "The path of the input folder on the left or the filelist. Whether checked or not, it will be used for subsequent training in this list.": "O caminho da pasta de entrada à esquerda ou a lista de arquivos. Independentemente de estar marcada ou não, ela será utilizada para o treinamento subsequente nesta lista.",
+  "Training Configuration": "Configuração de Treinamento",
+  "Training Error": "Erro de Treinamento",
+  "Training stopped": "Treinamento interrompido!",
+  "Type the path or select from the dropdown": "Digite o caminho ou selecione no menu suspenso",
+  "Use LoRA": "Usar LoRA",
+  "Use LoRA can save GPU memory, but may reduce the quality of the model": "O uso de LoRAs pode economizar memória da GPU, mas também pode reduzir a qualidade",
+  "Use filelist": "Usar lista de arquivos",
+  "VQGAN Configuration": "Configuração do VQGAN",
+  "View the status of the preprocessing folder (use the slider to control the depth of the tree)": "Visualizar o status da pasta de pré-processamento (use o controle deslizante para controlar a profundidade da árvore)",
+  "We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.": "Não nos responsabilizamos por qualquer uso indevido do modelo. Por favor, considere as leis e regulamentações locais antes de usá-lo.",
+  "WebUI Host": "Host da WebUI",
+  "WebUI Port": "Porta da WebUI",
+  "Whisper Model": "Modelo Whisper",
+  "You can find the source code [here](https://github.com/fishaudio/fish-speech) and models [here](https://huggingface.co/fishaudio/fish-speech-1).": "Você pode encontrar o código fonte [aqui](https://github.com/fishaudio/fish-speech) e os modelos [aqui](https://huggingface.co/fishaudio/fish-speech-1).",
+  "auto": "automático",
+  "bf16-true is recommended for 30+ series GPU, 16-mixed is recommended for 10+ series GPU": "bf16-true é recomendado para GPUs da série 30+, 16-mixed é recomendado para GPUs da série 10+",
+  "latest": "mais recente",
+  "new": "novo",
+  "This audio introduces the basic concepts and applications of artificial intelligence and machine learning.": "Este áudio introduz os conceitos básicos e aplicações de inteligência artificial e aprendizado de máquina.",
+  "You don't need to train this model!": "Não é necessário treinar este modelo!",
+  "Yes": "Sim",
+  "No": "Não",
+  "version:": "versão:",
+  "author:": "autor:"
+}